May 2025
Process Controls, Instrumentation and Automation
How to make your first $100 MM with digitalization
Digital transformation in the oil and gas industry has spurred a lot of interest from industry professionals over the last decade. However, the implementation of many of these projects has failed to impact the bottom lines of processing plants. While these projects may deliver technological integrations and flashy dashboards, the expected value from these projects may be missing. While this article will not explore the reasons for that, it will define a solid methodology to deliver value constantly.
Digital transformation in the oil and gas industry has spurred a lot of interest from industry professionals over the last decade. However, the implementation of many of these projects has failed to impact the bottom lines of processing plants. According to industry analysis, 70% of digital projects in the oil and gas industry “fail” to deliver value.1 While these projects may deliver technological integrations and flashy dashboards, the expected value from these projects may be missing. While this article will not explore the reasons for that, it will define a solid methodology to deliver value constantly.
Methodology. Even before a digitalization project is awarded, a list of strategies that should be implemented must be developed. Examples of these may include reducing energy costs, maximizing throughput and processing opportunity crudes, among others.
After developing such strategies, a list of key performance indicators (KPIs) should be compiled. To determine a baseline value, these KPIs must be trended over for at least 1 yr and then averaged out after removing outliers (FIGS. 1 and 2). The lagging KPIs are key to lagging KPI delivery; therefore, for each lagging KPI, a leading KPI must be determined that will be impacted by digital transformation. If this decision is made based only on lagging indicators, then the technology will display only those values and will not be able to impact them.
FIG. 1. Leading KPI: Diesel production rate from the hydrocracking unit (HCU).
FIG. 2. Lagging KPI.
Based on the developed strategies, the existing solution landscape must be evaluated to determine if a solution is already available in-house or if one can be developed to support the strategy. If a suitable technological solution is available, then the strategy should be executed via technology and the performance should be evaluated in real time via a KPI dashboard. For quick results, the strategy could be manually implemented first as proof of value (e.g., to ask for funds or dedicated internal resources from management). However, relying on only manual methods without digital transformation may not result in sustainable results. Digital transformation is necessary for maximum value achievement and sustainable results; therefore, a quick POV followed by a full-scale digital transformation is recommended. A visual representation of this process is illustrated in FIG. 3.
FIG. 3. A visual representation of the digital transformation process.
A real-world success story. The author’s company developed a strategy to maximize diesel production at its refinery by adjusting the cutpoint in the hydrocracking unit (HCU). However, before this cutpoint adjustment, its impact on the diesel network had to be evaluated—including the quality of the end product, the feed quality to the downstream units, and its impact on other product qualities and their respective pools, among other considerations.
To execute this initiative, there was no digital technology in-house to evaluate these possible impacts on the diesel network, so a decision was made to build an in-house, near-real-time optimizer with hybrid models to study these impacts (FIG. 4). The optimizer would be kept in near real time to consider shifting constraints, updated product tank lab results and tank levels, and changing market values of various products. The diesel network was modeled, and the optimum cutpoints were determined. The optimizer was synced with a proprietary visualization toola to obtain input values every minute, followed by an optimizer run to determine the new optimum. The solution was connected to a proprietary visualization toola dashboard to compare the optimum vs. the actual cutpoints, which were displayed to the operator together with their business impacts. This resulted in an immediate increase in diesel production by nearly 90,000 barrels per month (bbl/mos), valued at $6 MM/mos.
FIG. 4. In-house-built diesel pool optimizer. Note: For confidentiality reasons, the values shown are not real and are for demonstration purposes only.
The dashboard was further developed to retrieve data from siloed systems (e.g., planning, scheduling), the near-real-time optimizer and the actual advance process control (APC) system (FIG. 5). The dashboard also converted operating values to impacts on business operations, which, in essence, connected the enterprise level with the plant floor by translating these impacts. The aggregation of local to global impacts was provided at a higher level. Therefore, the digital solution provided greater visibility to executives, integrating the C-Suite to the plant floor via drill-down analytics. The plant floor data was converted to business information, and necessary targets were provided to plant floor personnel to maximize business outcomes, while executives were provided visibility on business improvement potential.
FIG. 5. The multi-system integrated KPI demonstration dashboard. Note: For confidentiality reasons, the values shown are not real and are for demonstration purposes only.
FIG. 6 shows how multi-system integration between previously siloed systems used digitalization to close the gap between operational targets. It was observed that the rolling plan’s target was the same as the near-real-time optimizer; however, the scheduling targets were misaligned. Utilizing optimizers, the gaps were closed among the schedule, actual operations and plan. This new dashboard was presented to stakeholders, who were in awe as to how the optimizer could achieve the increase in diesel without impacting the end product’s quality.
FIG. 6. Multi-system integration of different siloed systems used digitalization to close the gap between operational targets.
Following this successful limited solution, management approved the use of commercial digital twin-based solutions and integrated it with company visualization systems. Other similar strategies were developed that resulted in similar benefits.
Takeaways. A large percentage of digitalization projects fail to deliver sustainable value for various reasons. Most commonly, there may be an oversight into the constraints that stand in the way of value generation in the plant or people. To avoid such a scenario, the methodology presented in this article—planning the strategies, choosing the KPIs and completing a proof-of-value—is a better way to ensure the success of digital projects. This method ensures that the value of the digitalization project will begin to be generated even before the project is awarded, and that future constraints in both plant and people will be identified. This, in turn, will increase confidence in knowing that replicating the process at a greater scale will continue to result in a greater value. The remainder of the work will be to scope and ensure that the project’s quality control practices will be utilized so that vendors will understand and deliver the project to very stringent requirements. Ultimately, the generated value of the project can be used to fund the project, thus avoiding the need to plan a new budget.
NOTE
a AVEVA™ PI Vision™
LITERATURE CITED
1 Garcia, J., “Common pitfalls in transformations: A conversation with Jon Garcia,” McKinsey & Company, March 29, 2022, online: https://www.mckinsey.com/capabilities/transformation/our-insights/common-pitfalls-in-transformations-a-conversation-with-jon-garcia
Comments